About me

I am a PhD candidate at the University of Hong Kong, advised by Dr. Yanchao Yang and Prof. Kaibin Huang. Before joining HKU, I received my BSc in Mathematics and Applied Mathematics from the School of the Gifted Young, University of Science and Technology of China (USTC).

My research focuses on tabular foundation model pretraining, nonlinear correlation modelling, and LLM reasoning. I develop pretrained tabular models for mutual information, statistical dependence and density estimation, and study how relationships among hidden representations can help diagnose Transformer training.

My industry experience includes a Machine Learning QR internship at Minghong Investment (Aug–Oct 2026) and an External On-site Student Researcher role with Huawei’s HPC Group (RAFT) (Sep 2024–Jan 2026).

Research interests

• Tabular foundation model pretraining
• Nonlinear correlation modelling
• LLM reasoning

News

• October 2026 — Our team placed 2nd in Susquehanna (SIG)’s PhD Brainteaser Battle; I independently solved the competition’s hardest puzzle.
• September 2026 — Our team placed 1st in the Quant Challenge at Optiver Quant Focus, a three-day programme for PhD students. I independently solved 5 of the 12 mathematics and brainteaser problems.
• 2026 — InfoAtlas: A Foundation Model for Zero-Shot Statistical Dependence Estimate accepted to ICML 2026.
• May 2026 — Invited talk at HKU ECE: Foundation-style Methods for Real-Time Statistical Dependency Measurement and Its Applications.
• 2024 — InfoNet: Neural Estimation of Mutual Information without Test-Time Optimization accepted to ICML 2024 (Oral).

Contact

Email  /  Google Scholar  /  GitHub  /  English CV (PDF)  /  中文简历 (PDF)